One of the most difficult challenges in pattern recognition is data attribute selection process. Attribute selection played a critical role in dealing with high-dimensional problems and can be modeled as an optimization problem. Gery Wolf optimization algorithm is a recent swarm based algorithm, which is competitive to other bio-inspired algorithms. In this paper, a grey wolf optimizer is proposed as a wrapper attribute selection method. A V-shaped transfer function is employ to map a continuous search space to a discrete binary search space. Experimental results on eight UCI datasets shows the ability of the novel wrapper attribute selection algorithm in selecting the most informative attributes for classification tasks when compared to three well-known bio-inspired algorithms.