Clusters don't work like that. Clusters work by taking a large workload, breaking it into small pieces and farming them out to run on each of the clustered nodes. A cluster doesn't add processing power, it doesn't add RAM and it doesn't add speed for a general purpose workload.
The clustered workload has to be optimised for clustering and that's the hard part of the puzzle. Can you divide your database into partitions so that each cluster works on just a subset of data, can you aggregate the results set?
Note: Having anything humorous in your signature is completely banned on this forum. Wear a tin-foil hat and you'll get a ban.
Any DMs sent on Twitter will be answered next month.
This is a doctor free zone.