With large-scale Multiple-input Multiple-output (MOMO), we think of a system that use antenna arrays with an order of magnitude more elements than in systems being built nowadays, say a hundred antennas or more. As it is known that, the more antennas the transmitter/receiver is equipped with, the more the possible signal paths, the better the performance in terms of data rate and link reliability. However, channel estimation in large-scale MIMO is said to be hampered by the pilot contamination effect, constitute a major reduction for overall system performance. In this paper, we present a novel approach which tackles this problem by enabling a covariance formulation between cells during the channel estimation phase itself, could leads to improver the system performance. Here we present a noble scheme title as large-scale MIMO channel estimation based on circularly symmetric Gaussian covariance matrix. The numerical result shows the significance of proposed scheme.