"Run faster" is a subjective measure. The number you really need to be looking at is CPU and I/O cycles as other workload running on the system at the same time will impact your query performance. [As well as a measure referred to as parallel efficiency...]
Similarly, join paths, index selection and filter type... the absence or presence of statistics on the objects' underlying columns, and the freshness of those statistics... table skew... all come into play in terms of the optimizer being able to generate the most optimal plan for returning your request.
Basically, you need to do more information gathering to really understand what is going on with your system.