To investigate the neural activity corresponding to different cognitive states, it is of great importance to localize the cortical areas that are associated with task-related modulation. In this paper, we propose a novel discriminant pattern source localization (DPSL) method to analyze MEG data. Unlike most traditional source localization methods that aim to find "dominant" sources, DPSL is developed to capture the "differential" sources that distinguish different cognitive states. As will be demonstrated by the experimental results in this paper, the proposed DPSL method offers superior accuracy to identify the spatial locations of task-related sources.