How to speed up this federated query? - sparql

Question

I have a query which brings people who a dbo:Writer and have different birth-dates stated in DBpedia and Wikidata. I wrote it initially to be run independently but currently I'm running on Wikidata. It's quite slow and the interesting thing is that when I don't call with Wikidata endpoint with SERVICE, which I can afford to do here, it gets even slower. I'd be interested to learn why it is so. But my main question is, how to optimize it? Here is the query:
PREFIX owl: <http://www.w3.org/2002/07/owl#>
PREFIX rdfs: <http://www.w3.org/2000/01/rdf-schema#>
PREFIX dbo: <http://dbpedia.org/ontology/>
PREFIX dbp: <http://dbpedia.org/property/>
SELECT DISTINCT ?personDBP ?personWD ?personWDLabel ?BirthDateDBP ?BirthDateWD
WHERE {
SERVICE <http://dbpedia.org/sparql> {
?personDBP a dbo:Writer ;
dbo:birthDate ?BirthDate_DBP;
owl:sameAs ?personWD .
FILTER REGEX (?personWD, "wikidata.org")
BIND (xsd:date(?BirthDate_DBP) AS ?BirthDateDBP)
}
SERVICE <https://query.wikidata.org/sparql> {
?personWD wdt:P569 ?BirthDate_WD .
BIND (xsd:date(?BirthDate_WD) AS ?BirthDateWD)
}
FILTER (?BirthDateDBP != ?BirthDateWD)
SERVICE wikibase:label { bd:serviceParam wikibase:language "[AUTO_LANGUAGE],en". }
}
ORDER BY DESC(?BirthDateDBP)
LIMIT 50