A variety of real world applications fit into the broad definition of time series classification. Using traditional machine learning approaches such as treating the time series sequences as high dimensional vectors have faced the well known "curse of dimensionality" problem. Recently, the field of time series classification has seen success by using preprocessing steps that discretize the time series using a Symbolic Aggregate ApproXimation technique (SAX) and using recurring subsequences ("motifs") as features. In this paper we explore a feature construction algorithm based on genetic programming that uses SAX-generated motifs as the building blocks for the construction of more complex features. The research shows that the constructed complex features improve the classification accuracy in a statistically significant manner for many applications.