We propose a low complexity detection technique for multihead multitrack recording systems. By exploiting the sparseness of the two dimensional (2-D) partial response channel, we start with the development of an algorithm which performs belief propagation (BP) over the corresponding factor graph. We consider the BP-based detector not only for the partial response channel, but also for the more practical conventional media and bit-patterned media storage systems, with and without media noise. Compared to the maximum likelihood detector which has a prohibitively high complexity that is exponential with both the number of tracks and the number of ISI taps, the proposed detector has a much lower complexity and a fast parallel structure which come at a small performance penalty.