In this work, we are interested in studying uncertainty quantification (UQ) and global sensitivity analysis (GSA) in retrial queueing systems. Specifically, we investigate the M/G/1 retrial queue with priority customers, Bernoulli Schedule and general retrial times. We assume that the performance measures of the model are considered functions of input random parameters and approximated with polynomial chaos expansions (PCE). In order to perform GSA we use Sobol's indices which allow making an importance ranking of parameters. Several numerical results are provided and compared to MCS ones.