Within the BCI community, the opportunity to use BCI protocols to promote recovery of motor function by encouraging and guiding plasticity phenomena occurring after stroke (or more generally after brain injury) is at a very preliminary stage (for review see Birbaumer et al., 2008; Daly and Wolpaw, 2008; Mak and Wolpaw, 2010). Discussion is currently underway over several factors including: the extent to which patients have detectable brain signals that can support training strategies; which brain signal features are best suited for use in restoring motor functions and how these features can be used most effectively; and what the most effective formats are for the BCIs aimed at improving motor functions (for instance, what guidance should be provided to the user to maximize training that produces beneficial changes in brain signals). So far, preliminary findings are promising: Scherer et al. (2007a) suggested that event-related EEG activity time-frequency maps of event-related EEG activity and their classification are proper tools to monitor MI related brain activity in stroke patients and to contribute to quantify the effectiveness of MI. Buch et al. (2008) have shown that six out of eight chronic stroke patients suffering from a handplegia learned to control a magnetoencephalography-based BCI by MI. In all these cases, the best signals were depicted over the ipsilateral (unaffected hemisphere). Other attempts to use non-invasive BCI for rehabilitation include Ang et al. (2009) and Prasad et al. (2009). Finally, the idea that BCI technology can induce neuroplasticity has received remarkable support from the community based on invasive detection of brain electrical signals (for recent review see Wang et al., 2010).